ASA: Use of GSMA consumer RSP protocol in the IoT domain and its security implication

Tutor: Abu Shohel Ahmed

GSMA specified consumer RSP protocol, remotely provision SIM profiles to eUICCs located inside consumer eSIM devices. The protocol requires user interactions and assumed the eSIM device has an I/O interface. Recently, there are several initiatives to use the RSP protocol for low power IoT devices without having direct user interaction. As part of this topic, you will analyze existing proposals, and propose your idea to solve the problem.
References: 
  • https://www.gsma.com/esim/wp-content/uploads/2020/06/SGP.22-v2.2.2.pdf


AP: Formal Verification of Cryptographic Protocols

Tutor: Aleksi Peltonen

Formal verification is a group of techniques based on applied mathematics. These methods can be divided into two categories: (1) deductive and (2) model-based verification. Deductive verification involves inferring the correctness of a system specification with axioms and proof rules. Model-based verification, on the other hand, involves using a model checker to create a state model of the system and performing exhaustive state exploration to prove or disprove properties of the protocol. When an error or goal state is reached, the model checker typically provides a trace leading to it from the initial state. Formal verification methods are often used to prove the reliability of commonly used protocols, such as TLS 1.3, and they have been used by companies such as Amazon and Facebook to eliminate bugs in large-scale services. In this topic the student will learn about verification of cryptographic protocols with a state-of-the-art verification tool and demonstrate how it can be used to analyse a cryptographic protocol. The choice of tool and protocol will be agreed upon with the supervisor.

References: 

  • http://tamarin-prover.github.io/ 
  • https://prosecco.gforge.inria.fr/personal/bblanche/proverif/
  •  https://www.mcrl2.org/web/user_manual/index.html


AA: Causal reasoning in reinforcement learning

TutorAlexander Aushev
Can reinforcement learning agents learn performing and interpreting the experiments in the environment? Motivated by how human brains explore causal structures in the environment while doing a task, the field of causal reasoning in reinforcement learning tries to adapt this ability for agents. The necessity in causal reasoning naturally arises in biology, operational research, communications and, more generally, in all fields where the environment can be represented as a system of interconnected nodes. Recent developments in the field showed how inference of causal structures result in a more accurate and interpretable performance. For this topic you will review papers related to causal reasoning in reinforcement learning and focus on challenges, applications and state-of-the-art techniques of this field.

References:

  • Discovering latent causes in reinforcement learning: https://thesnipermind.com/images/Studies-PDF-Format/GershmanNormanNiv15.pdf
  • Gershman, Samuel J. "Reinforcement learning and causal models." The Oxford handbook of causal reasoning. Oxford University Press, 2017. 295 https://books.google.fi/books?hl=en&lr=&id=2qt0DgAAQBAJ&oi=fnd&pg=PA295&dq=causal+inference+in+reinforcement+learning&ots=azhyblbLVV&sig=hM5tQeK0fH8-yrOXpFesGSXRVc0&redir_esc=y#v=onepage&q=causal%20inference%20in%20reinforcement%20learning&f=false


AN: Auto time series forecasting for the regression problems

Tutor: Alexander Nikitin
Modern machine learning tools become more straightforward for users without any background knowledge. AutoML techniques make it possible to automatically construct the model (choose the model type, architecture, hyperparameters). The goal of this project is to review existing methods for time series regression problems and propose a way to automatically construct solutions for any particular dataset. Prerequisite: Basic understanding of machine learning and mathematics, good knowledge of Python (or Julia, or R, or MatLab).

References:

  • https://ai.googleblog.com/2020/12/using-automl-for-time-series-forecasting.html
  • https://www.usenix.org/conference/opml20/presentation/huang 
  •  https://towardsdatascience.com/time-series-forecasting-neuralprophet-vs-automl-fa4dfb2c3a9e


AYJ: WEB-based mobile augmented reality

Tutor: Antti Ylä-Jääski

Augmented reality running on mobile devices usually is based on Apps that are built from ARCore, ARKit, Unity, etc. Web-based AR (Web AR) implementation can provide a pervasive Mobile AR experience to users thanks to the many successful deployments of the Web as a lightweight and cross-platform service provisioning platform. Furthermore, the emergence of 5G mobile communication networks has the potential to enhance the communication efficiency of Mobile AR dense computing in the Web-based approach. This topic asks the student to make a survey of the challenges and opportunities for web-based mobile augmented reality. This work can be completed as a sole literature survey, however, there is also a possibility to make a small-scale web-based mobile augmented reality experimental part.

References:

  • 2019 Proceedings of the IEEE 107(4):1-16 Web AR: A Promising Future for Mobile Augmented Reality - State of the Art, Challenges, and Insights https://ieeexplore.ieee.org/document/8643424 
  •  2020 IEEE Transactions on Cloud computing Edge AR X5: An Edge-Assisted Multi-User Collaborative Framework for Mobile Web Augmented Reality in 5G and Beyond https://ieeexplore.ieee.org/abstract/document/9300168
  •  Augmented reality for the web https://developers.google.com/web/updates/2018/06/ar-for-the-web



BL1: Adversarial machine learning defenses

Turtor: Blerta Lindqvist

Neural network classifiers are susceptible to attacks that cause misclassification. Many of the proposed defenses have been disputed, leaving only few standing.

References:

  • https://nicholas.carlini.com/writing/2019/all-adversarial-example-papers.html


Bl2:Adversarial machine learning attacks

Turtor: Blerta Lindqvist

Neural network classifiers are susceptible to attacks that cause misclassification. There are several categories of attacks. The current strongest attack is the CarliniWagner attack.

References:

  • https://nicholas.carlini.com/writing/2019/all-adversarial-example-papers.html



BGAT: Robustness and Privacy in Federated Learning

Tutor: Buse Gul Atli Tekgul

Federated learning is a distributed machine learning setting, where training is done on edge devices owned by clients and coordinated via a central server or a service provider [1,2]. Federated learning allows clients to store their own data locally; therefore, it does not compromise the privacy of clients’ data. Today companies like NVIDIA and Google has federated learning settings and clients (e.g., owner of cell-phone devices) both participate the training and get personalised apps without worrying about possible leakage of their sensitive datasets. Recent work has shown that, since the model is downloaded by clients participating to training, they can implement different adversarial attacks against federated learning models [3]. There have been attacks against the integrity: Poisoning attacks [5] aim to manipulate the model parameters such that its performance degrades completely or on some specific samples. Another well-known attack type is attacks against confidentiality: Malicious clients (or a malicious server) exploit the vulnerabilities of the learning algorithm in order to get information about other client's data [4]. In this seminar topic, the student(s) are expected to do a survey of attacks and defences related to the robustness and privacy of the federated learning.

References:

  • [1] Bonawitz, Keith, et al. "Towards federated learning at scale: System design." arXiv preprint arXiv:1902.01046 (2019). 
  • [2] McMahan, Brendan, et al. "Communication-efficient learning of deep networks from decentralized data." Artificial Intelligence and Statistics. PMLR, 2017. 
  • [3] Kairouz, Peter, et al. "Advances and open problems in federated learning." arXiv preprint arXiv:1912.04977 (2019).
  •  [4] Nasr, Milad, Reza Shokri, and Amir Houmansadr. "Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning." 2019 IEEE Symposium on Security and Privacy (SP). IEEE, 2019. 
  • [5] Fang, Minghong, et al. "Local model poisoning attacks to Byzantine-robust federated learning." 29th {USENIX} Security Symposium ({USENIX} Security 20). 2020.

CY: Uncertainty Quantification in Neural ODE Models

Tutor: Cagatay Yildiz

Recently proposed neural ordinary differential equation (NODE) models have been revolutionary in continuous time modeling. The idea is to approximate unknown time differentials, or drift functions, via neural networks, which leads to computing the (time) integral of a neural network. This method allows learning any continuous-time phenomena, such as walking/running sequences and many physical systems involving differential equations. One aspect of continuous-time modelling that is not well-investigated is uncertainty quantification. In ODE2VAE paper (see below), we used Bayesian neural networks (BNN) to handle uncertainty over the unknown time differential function. Possible other alternatives could be implicit BNNs, deep ensembles, functional BNNs, etc. In this project, we would like to investigate whether these methods work in practice and which is more advantageous and why.

References:

  • Neural ordinary differential equations: https://arxiv.org/pdf/1806.07366.pdf 
  •  ODE2VAE: Deep generative second order ODEs with Bayesian neural networks: https://arxiv.org/pdf/1905.10994.pdf 
  •  Deep Ensembles: https://papers.nips.cc/paper/2017/file/9ef2ed4b7fd2c810847ffa5fa85bce38-Paper.pdf


ER: Semantic description of policies for intelligent services in distributed environments

 Tutor: Edgar Ramos

Policies targeting how a device can be used or who is allowed to do what with the device and what kind of operations are allowed or should be enforced with the data are needed to manage IoT devices that run intelligence services. A high-level description of these policies can be provided to devices and translated to concrete policies that the device can understand (for example, read, write, id requirements, etc). One approach in this direction is the use of semantics descriptions to provide such policies using for example semantic constructions with a descriptive language. The IoT applications are inherently heterogeneous and their capacity to interpreter high-level policies is limited to their domain. Therefore domain of application should be also taken care in the definition and interpretation of such policies. 

References: 

  • AWS idAM is quite an interesting implementation in this direction (https://docs.aws.amazon.com/IAM/latest/UserGuide/intro-structure.html) An article on policy semantics language description: Kagal L., Finin T., Joshi A. (2003) 
  • A Policy Based Approach to Security for the Semantic Web. In: Fensel D., Sycara K., Mylopoulos J. (eds) The Semantic Web - ISWC 2003. ISWC 2003. Lecture Notes in Computer Science, vol 2870. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39718-2_26
  • Policy language from AWS : https://docs.aws.amazon.com/IAM/latest/UserGuide/iam-ug.pdf#reference_policies_grammar



GI: Foveated Video Quality Metrics

Tutor: Gazi Illahi
Foveated video encoding (FVE) refers to video encoding where spatial quality of each video frame corresponds to visual acuity of the Human Visual System (HVS) which is non-uniform. This type of encoding requires the encoder to know (detected or predicted) gaze location of the viewer on the video frame. The motivation for FVE is the theoretical ability to reduce size of a video frame without reducing the perceptual quality of the video frame. The best way to measure the quality of an encoded video is through subjective tests, however, subjective studies are costly and time consuming. It is common to use objective computational metrics to measure video quality. Such methods include simple error metrics like mean square error PSNR and more complex methods which take into account the HVS, like SSIM, VMAF etc. However, there are few universal objective quality metrics for Foveally encoded video. The student's task would be to do a literature review of all objective video quality metrics specifically designed to measure quality of Foveally encoded video.

  • 1.Lee, Sanghoon, Marios S. Pattichis, and Alan C. Bovik. "Foveated video quality assessment." IEEE Transactions on Multimedia 4, no. 1 (2002): 129-132. 
  • 2. Jin, Yize, et al. "Study of 2D foveated video quality in virtual reality." Applications of Digital Image Processing XLIII. Vol. 11510. International Society for Optics and Photonics, 2020. 
  • 3. S. Rimac-Drlje, G. Martinović and B. Zovko-Cihlar, "Foveation-based content Adaptive Structural Similarity index," 2011 18th International Conference on Systems, Signals and Image Processing, Sarajevo, 2011, pp. 1-4.

HD: TinyML as-a-Service - bringing Machine Learning inference to the deepest IoT edge

Tutor: Hiroshi Doyu

TinyML, as a concept, concerns the running of ML inference on Ultra Low-Power (ULP ~1mW) microcontrollers found on IoT devices. Yet today, various challenges still limit the effective execution of TinyML in the embedded IoT world. As both a concept and community, it is still under development. Here at Ericsson, the focus of our TinyML as-a-Service (TinyMLaaS) activity is to democratize TinyML, enabling manufacturers to start their AI businesses using TinyML, which runs on 32 bit microcontrollers. Our goal is to make the execution of ML tasks possible and easy in a specific class of devices. These devices are characterized by very constrained hardware and software resources such as sensor and actuator nodes based on these microcontrollers. The core componet of TinyMLaaS is Machine Learning Compiler (ML compiler)

References:

  • https://youtu.be/m2sHB4DOfMg https://youtu.be/yqO6bl8rBEY https://www.mindmeister.com/1637137991?t=QfRudlGYBy
  • https://osseu19.sched.com/event/TLCJ https://static.sched.com/hosted_files/osseu19/f9/elc2019-tinymlaas.pdf
  • https://www.ericsson.com/en/blog/2019/12/tinyml-as-a-service-iot-edge https://www.ericsson.com/en/blog/2019/12/tinyml-as-a-service
  • https://www.ericsson.com/en/blog/2020/2/how-can-we-democratize-machine-learning-iot-devices


JH1: Instrumentation of Distributed Computing Systems

Tutor:  Jaakko Harjuhahto

Instrumentation is the ability to measure a system. Monitoring uses instrumentation to answer the questions, what is the current state of a distributed computing system and the applications running on the system? What is the resource utilization (CPU, memory, IO, network etc) of the system? What are the most recent system events? Are there any symptoms of problems, and what are the root causes? How to follow flows of data and actions across nodes, i.e. perform tracing? The task is to perform a survey of academic work on the current state of distributed system instrumentation and monitoring. The focus should be on IoT and fog computing [1], where the systems can be highly heterogenous and geo-distributed.

Common practical tools: 
  • - Prometheus, https://prometheus.io/ 
  • - OpenTracing, https://opentelemetry.io/ 
  •  The TICK stack, https://www.influxdata.com/time-series-platform/ 
 References:
  •  [1] Yousefpour & al. All One Needs to Know about Fog Computing and Related Edge Computing Paradigms - A Complete Survey. Journal of Systems Architecture. https://doi.org/10.1016/j.sysarc.2019.02.009


JH2: Simulating 5G for Distributed System Communications

Tutor:  Jaakko Harjuhahto

The task is to perform a literature study to review approaches for simulating 5G connectivity between two computers, from the point-of-view of these computers. If one computer wants to send a number of bytes via 5G to another computer connected to the same base station, how long will this take depending base station configuration, signal strength, overall network load etc? The focus is on system level or end-to-end simulation: how 5G behaves from a user's perspective. An example use case for this type of use is [1].

Practical simulators: 

  •  NS-3, https://www.nsnam.org/ 
  •  OmNet++, https://omnetpp.org/ 
  •  Vienna 5G Link Level Simulator, [2] 
  • iFogSim, [3] 
 References:

  •  [1] Harjuhahto, Debner, Hirvisalo. Processing LiDAR Data from a Virtual Logistics Space. Fog-Iot 2020. https://doi.org/10.4230/OASIcs.Fog-IoT.2020.4
  •  [2] Pratschner, S., Tahir, B., Marijanovic, L. et al. Versatile mobile communications simulation: the Vienna 5G Link Level Simulator. https://doi.org/10.1186/s13638-018-1239-6 
  • [3] Gupta, Dastjerdi, Ghosh, Buyya. iFogSim: A toolkit for modeling and simulation of resource management techniques in the Internet of Things, Edge and Fog computing environments. https://doi.org/10.1002/spe.2509


JB: Service enumeration techniques in microservices architectures

Tutor: Jacopo Bufalino

After attackers gain a foothold in an information system, they will want to map the system and discover further targets. The most common next step is to run tools like nmap to enumerate the hosts and open ports in the local network. As services move from the local network to cloud platforms, the goal could be to map the cloud infrastructure and microservices. Fingerprinting and even machine learning techniques can be used to identify the reachable services and their software stack. The goal if this thesis is to survey the available enumeration techniques, understand their operating principles, and optionally to apply them in a specific target environment.

References: 

  • https://kubernetes.io/ 
  • https://subscription.packtpub.com/book/networking_and_servers/9781783289592/4/ch04lvl1sec30/service-enumeration
  •  https://istio.io/

JR1: Proof systems for the propositional logic

Tutor: Jussi Rintanen

Proof systems for the propositional logic seem to have a close connection to the algorithms for solving the satisfiability problem of the propositional logic. The goal of the project is to investigate these relations and the newest research results in the area, for example the connection between the CDCL algorithm for satisfiability and the general resolution rule for the propositional logic.

References: 

  • On the interplay between proof complexity and SAT solving J Nordström - ACM SIGLOG News, 2015


JR2: Safety of cryptographic hash functions and approaches to break them

Tutor: Jussi Rintanen

Cryptographic hash functions such as SHA3 are widely used, and believed to be unbreakable. No proof of their unbreakability exists, and such a proof would presumably imply P != NP which is considered unlikely. One proposed approach to breaking SHA3 is to use automated reasoning methods for the propositional satisfiability problem SAT. Although SAT is an NP-complete problem, for many application categories best algorithms for SAT scale up to thousands and thousands variables. The project investigates the basis of the claims of the security of SHA3 and related methods, including SAT-based approaches to attempt to break it.

References: 

  • Security margin evaluation of SHA-3 contest finalists through SAT-based attacks E Homsirikamol, P Morawiecki, M Rogawski


JR3: Software package management with SAT and other combinatorial search methods

Tutor: Jussi Rintanen

Software configuration management is a hard problem that shows up in operating systems that support the automated installation of software packages that have complex dependency and incompatibility relations between them. When installing a new software package, it has to be checked that the new package and other packages it requires are compatible with existing packages, and whether possible conflicts between packages can be resolved. This problem is NP-hard, and in general requires the use of combinatorial search methods. The goal of the works is to investigate the software package management problem and methods for solving it, for example reductions to the satisfiability problem SAT.

References: 

  • Towards efficient optimization in package management systems A Ignatiev, M Janota, J Marques-Silva


JR4: Reduction of relational calculus queries to relational algebra and SQL

Tutor: Jussi Rintanen

The goal of the work is to develop a reduction from a general class of relational calculus queries to relational algebra and its extensions as implemented in the SQL language. Relational calculus is often a preferred way of expressing complex queries, but does have widely available query methods in existing database systems. The work investigates the possibilities of reducing general relational queries to SQL. Queries with limited quantification are reducible to basic relational algebra, but more complex features, including universal quantification, seem to require features like aggregation as present in SQL.

References:

  • Equivalence of relational algebra and relational calculus query languages having aggregate functions A Klug - Journal of the ACM (JACM), 1982


LC: Approaches to building secure software systems

Tutor: Lachlan Gunn

Developing secure software is difficult, and is made more difficult by the fact that many situations require the use of unsafe languages such as C and C++, where an error by the programmer can allow memory corruption and so arbitrary code execution. Programmers have a number of tools at their disposal to help them build secure systems: development practices, analysis tools, memory-safe languages, code generators, and low-level defences inserted by the compiler. In this project, each student will survey the literature relating to one or more aspects of secure software development, identifying what are the current state-of-the-art techniques available to today's software developers.

References:

  • Memory corruption vulnerabilities: https://doi.org/10.1109/SP.2013.13 
  •  Some of our own research into using hardware to defend against these vulnerabilities: https://ssg.aalto.fi/research/projects/harp/ 
  •  seL4, a formally-verified operating system: https://sel4.systems/ HACL*, a formally-verified cryptographic library: https://eprint.iacr.org/2017/536.pdf



LA: Learning to communicate optimally

Tutor:  Laia Amoros

Reliability and security in communication systems is traditionally treated using tools from information theory and coding theory, where mathematical formulas are derived for a few rigid communication models. A novel approach to this setup is to use different machine learning techniques to optimize reliability and security without previously assuming any channel characteristics.

References: 

  • Several directions can be taken depending on the student's interests. 
  •  https://wisec2020.ins.jku.at/proceedings-wiseml/wiseml20-96.pdf 
  •  https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8890904


MK: Real-time networking

Tutor: Miilka Komu
Real-time Linux [1,2] is one of the most famous projects trying address real-time computational needs. However, real-time networking has not received so much attention.The goal of this paper is write a literature overview of the state of the art related to real-time networking, which is mostly related to deterministic networks (DETNET) work in the IETF [5,6] and Time-Sensitive Networking [7]. The student should explain how the standards are connected together, and describe also some relevant implementations [3,4] as well.

References: 
  • [1] https://static.lwn.net/images/conf/rtlws11/papers/proc/p20.pdf
  •  [2] https://www.slideshare.net/Saruspete/linux-rt-in-financial-markets
  •  [3] https://news.developer.nvidia.com/new-real-time-smartnic-technology-5t-for-5g/ 
  •  [4] https://developer.nvidia.com/blog/transforming-next-gen-wireless-with-5t-for-5g-and-aerial-sdk/ 
  •  [5] https://datatracker.ietf.org/wg/detnet/about/ 
  •  [6] https://datatracker.ietf.org/doc/rfc8655/ 
  •  [7] https://1.ieee802.org/tsn/

MS1: Security for Dynamic Host Configuration Protocol (DHCP)

Tutor: Mohit Sethi

Dynamic Host Configuration Protocol (DHCP) is a network configuration protocol used for providing IP addresses to devices joining a network. DHCP servers typically also provide additional information such as default gateway, DNS servers etc. In this seminar topic, the student is expected to perform a literature survey on protocols as well as industry best practices for enhancing the security of DHCP.

References:

  • [1] https://tools.ietf.org/html/rfc3118 
  • [2] https://tools.ietf.org/html/draft-xu-dhc-cadhcp-00 
  • [3] https://www.cioreview.com/news/how-to-secure-a-network-from-dhcp-attacks-nid-15482-cid-21.html 
  • [4] https://www.serverbrain.org/network-services-2003/lesson-applying-security-guidelines-for-dhcp.html 
  • [5] Duangphasuk, Surakarn, Supakorn Kungpisdan, and Sumeena Hankla. "Design and implementation of improved security protocols for DHCP using digital certificates." 2011 17th IEEE International Conference on Networks. IEEE, 2011.

MS2: Analyzing unknown, unexpected, and sometimes unwanted features in modern messaging protocols and platforms

Tutor: Mohit Sethi

Covid-19 forced large swathes of the global population to work from home and rely on modern messaging and meeting platforms such as Zoom, Microsoft Teams, Skype, Skype for business, Facebook meeting rooms etc. Each tool has its unique quirks and features. Many users aren't always aware of all the features and their correct usage. This can lead to often unexpected behavior and sometimes embarrassing situations such as: * Adding a new colleague to an existing group chat which may have included some sensitive discussion about him/her * A teacher joins a breakout room in zoom but is unaware of the chat discussion among students on returning to the main call In this topic, the student is expected to fully explore all the features of the different messaging and meeting tools. The student can also explore features which could be incorporated in future versions. For instance, providing users with more control on who can read chat messages sent in the past etc.

References:
  • [1] https://zoom.us/features
  •  [2] https://www.technology.pitt.edu/blog/chat

NW1: ABC (Approximate Bayesian Computation) methods for Cognitive Neuroscience

 Tutor:  Nitin Williams

Recent modelling efforts in Cognitive Neuroscience have furnished insight into mechanisms generating human Neuroscience data. However, fitting these models to experimental human Neuroscience data has been hampered by the intractability of the model likelihood functions. Likelihood-Free Inference (LFI) techniques from Approximate Bayesian Computation (ABC) have shown promise in addressing these issues. However, several variants of ABC have been proposed in the literature, making it difficult to choose which one to deploy. In this project, you will review the different variants of ABC proposed in the literature and weigh their pros and cons. You will also develop recommendations on which are most suitable for fitting models in Cognitive Neuroscience in order to gain insight on mechanisms producing the data. Finally, particularly promising ABC techniques could be compared using simulations. You will be part of the Probabilistic Machine Learning group. Prerequisites The project would be ideal for someone with knowledge of Probability and Machine Learning and an interest in Cognitive Neuroscience. Python programming experience would be useful but not essential.

References:

  • Hadida et al. (2018) "Bayesian optimization of large-scale biophysical networks" NeuroImage 174: 219-236


NW2: LFI (Likelihood-Free Inference) techniques for Cognitive Neuroscience

Tutor:  Nitin Williams

Recent modelling efforts in Cognitive Neuroscience have furnished insight into mechanisms generating human Neuroscience data. However, fitting these models to experimental human Neuroscience data has been hampered by the intractability of the model likelihood functions. Likelihood-free inference (LFI) techniques have shown promise in addressing these issues. However, the plethora of LFI methods proposed in the literature makes it difficult to choose which one to deploy. In this project, you will review the different LFI approaches proposed in the literature and weigh their pros and cons. You will also develop recommendations on which are most suitable for fitting models in Cognitive Neuroscience in order to gain insight on mechanisms producing the data. Finally, particularly promising LFI approaches could be compared using simulations. You will be part of the Probabilistic Machine Learning group. Prerequisites The project would be ideal for someone with knowledge of Probability and Machine Learning and an interest in Cognitive Neuroscience. Python programming experience would be useful but not essential.

References: 

  • Cranmer et al. (2020) "The frontier of simulation-based inference" PNAS 117(48):30055-30062



PM: Bayesian preference learning and recommender systems

Tutor: Petrus Mikkola

The recent Bayesian machine learning techniques, which are build upon psychometrics and the economic utility theory, enable efficient preference learning and belief elicitation. The fundamental idea is to model the user’s latent valuation function (aka utility function) as a Gaussian process. From the application perspective, the research is closely related to recommender systems. The two main types of recommender systems are based on similarity computations over users (collaborative filtering) or over items (content-based filtering). The latter relates to the same problem that can be dealt with Bayesian preference learning. The goal of the thesis is to synthesize the research on recommender systems and Bayesian preference learning into a coherent literature review. Furthermore, it is possible to conduct an experimental comparison of reviewed methodologies.

References: 

  • https://dl.acm.org/doi/10.1145/1102351.1102369 
  • https://arxiv.org/abs/1704.03651 
  • https://link.springer.com/chapter/10.1007/978-0-387-85820-3_1


RM1: Predict unplanned events with Twitter data

Tutor:  Rongjun Ma

Social media has been nowadays employed as a source of information for event detection. Better understanding these unplanned events in advance helps related departments to take timely actions, such as quick response to traffic congestions. Twitter, as a real-time social media, is widely researched for many use cases. Students will investigate these different use cases, try to summarize, and answer the research questions: What event attributes (geolocation, time, crowd size, etc.) can or can’t we get from Twitter, and how do we extract the information?

References:

  • [1] Goh, G., Koh, J. Y., & Zhang, Y. (2018, November). Twitter-Informed Crowd Flow Prediction. In 2018 IEEE International Conference on Data Mining Workshops (ICDMW) (pp. 624-631). IEEE. http://kohjingyu.com/papers/Twitter_Informed_ICDM2018.pdf
  •  [2] Ying, Y., Peng, C., Dong, C., Li, Y., & Feng, Y. (2018, August). Inferring event geolocation based on Twitter. In Proceedings of the 10th International Conference on Internet Multimedia Computing and Service (pp. 1-5). https://dl.acm.org/doi/pdf/10.1145/3240876.3240909?casa_token=v11zTBWLgGEAAAAA:HFeOfzYTMXvh6h36cKAdBSGdkvevFt2oQqWQJ1ATxRevNLbIMOePmkl-nW4ktmRgG819N5IR-h-F
  •  [3] D'Andrea, E., Ducange, P., Lazzerini, B., & Marcelloni, F. (2015). Real-time detection of traffic from twitter stream analysis. IEEE transactions on intelligent transportation systems, 16(4), 2269-2283.


RM2: How do people make privacy decisions

Tutor:  Rongjun Ma

With the rapid growth of the internet, more and more individual information is exposed to the network. Inevitably, Privacy becomes a concern for everyone’s daily life as the disclosure of personal info might lead to financial or even physical attacks. What are the risks related to privacy issues that people are facing nowadays? And what are the factors people consider when making their privacy decisions? These are the research questions to be answered under this topic.

References: 
  • [1] Adjerid, I., Peer, E., & Acquisti, A. (2016). Beyond the privacy paradox: Objective versus relative risk in privacy decision making. Available at SSRN 2765097. 
  •  [2] Acquisti, A., & Grossklags, J. (2007). What can behavioral economics teach us about privacy. Digital privacy: theory, technologies and practices, 18, 363-377. https://www.heinz.cmu.edu/~acquisti/papers/Acquisti-Grossklags-Chapter-Etrics.pdf 
  •  [3] Toch, E., Wang, Y., & Cranor, L. F. (2012). Personalization and privacy: a survey of privacy risks and remedies in personalization-based systems. User Modeling and User-Adapted Interaction, 22(1-2), 203-220.

SDP1: Tractable Deep Density Estimation with SPNs

Tutor: Sebastiaan De Peuter

Sum-product networks (SPNs) [1] are a class of deep probabilistic models for modeling joint densities. SPNs are tree-like computational structures containing sum nodes and product nodes where values flow from children to their parents. SPNs can be interpreted as latent variable models or as very large mixtures of factorization of the density they model. What makes SPNs interesting is that they allow you to tractably calculate any marginal and conditional of the joint density they model, which can be used to for example learn to complete images. Furthermore they naturally support a mixture of discrete and continuous variables. Parameters can be determined by gradient-based methods but learning the right structure for an SPN is still an area of active research (see [2] for a recent example). The goal for this project is for you to do a survey of the SPN literature, paying special attention to what novel applications SPNs have enabled. For the practically inclined this project can also involve a novel application or a comparison of SPN inference methods. The project will be carried out in the PML research group.

References: 
  • [1] https://ieeexplore.ieee.org/abstract/document/6130310
  • [2] http://papers.nips.cc/paper/8864-bayesian-learning-of-sum-product-networksx

SDP2: Contextual Bandit Algorithms

Tutor: Sebastiaan De Peuter

Bandit problems are stateless decision problems where you are given a set of options (arms) to choose from but are not told how good each option is. In every iteration you choose an option and then receive a reward for that option. Over time you can use these rewards to estimate the value of every option. The goal in bandit problems is to maximize the sum of rewards over time, this requires trading off exploration (trying out options to observe their reward) and exploitation (using the best known option currently to get guaranteed high reward). This project will be about contextual bandits, which is a variant of the original problem where at every iteration you are given a "context", some additional information to make your choice, which also determines the reward of the different options. An example of a contextual bandit problem is an assistance problem where at every iteration you have to help a user whose type is given by the context. Different types of users require different kinds of assistance so the value of your assistance options depends on the user type. In this project you will survey contextual bandit algorithms and apply them to a real problem. The project is flexible. If you don't currently have a good background in RL or bandit algorithms you can do a literature survey, supplemented with an application if time permits. If you have more background or are a quick learner then we have a real project related to the example from above which you can tackle. The project will be carried out in the PML research group.

References:

  • https://tor-lattimore.com/downloads/book/book.pdf

 




SJ: Benchmarking MIMIC-IV medical code prediction with NLP models

Tutor: Shaoxiong JI
Automatic medical code assignment is a routine healthcare task for medical information management and clinical decision support. The International Classification of Diseases (ICD) coding system, maintained by the World Health Organization (WHO), is widely used among various coding systems. Thus, the medical code assignment task is also called ICD coding. It uses clinical notes of discharge summaries to predict medical codes in a supervised manner with human-annotated codes, which is formulated as a multi-class multi-label text classification problem in the medical domain. This project conducts a benchmarking study on the new MIMIC-IV dataset with NLP and deep learning, specifically, neural attention models and multitask learning.

References: 
  • https://www.nature.com/articles/s41597-019-0103-9 https://mimic-iv.mit.edu

TG: Adversarial examples for large pre-trained NLP models

Tutor:  Tommi Gröndahl
Large pre-trained neural networks have become the state-of-the-art in machine learning, particularly in natural language processing (NLP). The most prevalent of such pre-trained NLP models are BERT [1] and its derivatives, and GPT(-2/3) [2]. While these models show good performance in e.g. language classification and generation, they have been demonstrated to be vulnerable to adversarial attacks [3, 4, 5]. The aim of this project is to survey existing research on constructing adversarial examples for large pre-trained NLP models, and analyze some of the possible reasons for the success of such attacks.

References: 
  • [1] https://arxiv.org/abs/1810.04805 
  • [2] https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf 
  • [3] https://arxiv.org/pdf/2004.09984.pdf
  •  [4] https://arxiv.org/abs/2010.05648
  •  [5] https://arxiv.org/abs/1908.07125

TA: Recent developments security protocol standards

Tutor:  Tuomas Aura

The goal of this topic is to investigate the recent developments in security protocols standardization. You will learn both about a specific protocol and about the standardization process. The standards of interest include the IETF security area (e.g. Messaging layer security mls, Web Authorization Protocol OAuth, transport layer security TLS) , IEFT 802.11 (Wi-Fi 6), and Bluetooth (mesh networks, applications to location beacons and contact tracing). The project will require the student to learn to read standards literature, draft specification (where available), and to find supporting research papers. Up to 6 students can choose this topic. Each student will focus on one specific technology or new development, which will be agreed with the supervisor.

References: 

  • Active IETF Working Groups: https://datatracker.ietf.org/wg/, see the security area 
  •  IEEE 802.11: https://www.ieee802.org/11/ 
  •  Bluetooth: https://www.bluetooth.com/specifications/



VTB: Resource allocation using game theory in LPWAN

Tutor: Verónica Toro Betancur

Games theory has been widely used to make desicions in businesses and economy. However, this theory has proven to be useful to model agents in wireless networks as well. The common approach is to model the network as a set of players (devices) who are looking for the best payoff for themselves. This can be done by either cooperating with other players or compiting with all of them. By doing so, each player will end up choosing its own optimal set of resources. This topic focuses on this kind of game theory approaches in LPWAN (Low Power Wide Area Networks) in general but mainly in LoRa. The task is to write a review paper describing up-to-date articles in this field. There are not really prerequisites for this topic but the student should be willing to learn about game theory.

References:

  • P. Kumari, H. P. Gupta and T. Dutta, "Estimation of Time Duration for Using the Allocated LoRa Spreading Factor: A Game-Theory Approach," in IEEE Transactions on Vehicular Technology, vol. 69, no. 10, pp. 11090-11098, Oct. 2020, doi: 10.1109/TVT.2020.3007566. 
  •  P. Kumari, H. P. Gupta and T. Dutta, "An Incentive Mechanism-Based Stackelberg Game for Scheduling of LoRa Spreading Factors," in IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2598-2609, Dec. 2020, doi: 10.1109/TNSM.2020.3027730. 
  •  M. Haghighi, Z. Qin, D. Carboni, U. Adeel, F. Shi and J. A. McCann, "Game theoretic and auction-based algorithms towards opportunistic communications in LPWA LoRa networks," 2016 IEEE 3rd World Forum on Internet of Things (WF-IoT), Reston, VA, 2016, pp. 735-740, doi: 10.1109/WF-IoT.2016.7845517. 
  •  A. Tolio, D. Boem, T. Marchioro and L. Badia, "Spreading Factor Allocation in LoRa Networks through a Game Theoretic Approach," ICC 2020 - 2020 IEEE International Conference on Communications (ICC), Dublin, Ireland, 2020, pp. 1-6, doi: 10.1109/ICC40277.2020.9149174. 
  • A. Tolio, D. Boem, T. Marchioro and L. Badia, "A Bayesian Game Framework for a Semi-Supervised Allocation of the Spreading Factors in LoRa Networks," 2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York City, NY, 2020, pp. 0434-0439, doi: 10.1109/UEMCON51285.2020.9298137.


WM: Machine Learning-based Traffic Flow Prediction

Tutor: Wencan Mao
Traffic flow prediction has been a heated application domain of machine learning-based algorithms. What are the features of these algorithms? For example, which neural networks do they use? What is the time range of prediction (short term/long term)? What are the suitable deployment scenarios? What are the pros. and cons. of the algorithms?

  • [1] Luo, X., Li, D., Yang, Y. and Zhang, S. (2019). Spatiotemporal Traffic Flow Prediction with KNN and LSTM. Hindawi Journal of Advanced Transportation, Volume 2019, Article ID 4145353, 10 pages. 
  • [2] Z. Zheng, Y. Yang, J. Liu, H. Dai and Y. Zhang (2019). Deep and Embedded Learning Approach for Traffic Flow Prediction in Urban Informatics," in IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 10, pp. 3927-3939, Oct. 2019. 
  • [3] Z. Cui, K. Henrickson, R. Ke and Y. Wang (2018). Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting, in IEEE Transactions on Intelligent Transportation Systems. 
  • [4] B. Yu, H. Yin and Z. Zhu (2017). Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI-18). 
  • [5] X. Di, Y. Xiao, C. Zhu, Y. Deng, Q. Zhao and W. Rao (2019). Traffic Congestion Prediction by Spatiotemporal Propagation Patterns, 2019 20th IEEE International Conference on Mobile Data Management (MDM), Hong Kong, Hong Kong, 2019, pp. 298-303. 
  • [6] Q. Xie, T. Guo, Y. Chen, Y. Xiao, X. Wang and B.Y. Zhao (2019). How do urban incidents affect traffic speed? A Deep Graph Convolutional Network for Incident-driven Traffic Speed Prediction.









Last modified: Tuesday, 26 January 2021, 10:08 AM